Computer Vision
Extracting meaning and building representations of visual objects and events in the world.
Our main research themes cover the areas of deep learning and artificial intelligence for object and action detection, classification and scene understanding, robotic vision and object manipulation, 3D processing and computational geometry, as well as simulation of physical systems to enhance machine learning systems.
Quick Links
-
Researchers
Jeroen
van Baar
Tim
Marks
Michael
Jones
Alan
Sullivan
Matthew
Brand
Anoop
Cherian
Chiori
Hori
Ronald
Perry
Takaaki
Hori
Hassan
Mansour
Jay
Thornton
Siheng
Chen
Devesh
Jha
Petros
Boufounos
Radu
Corcodel
Daniel
Nikovski
Arvind
Raghunathan
Diego
Romeres
Anthony
Vetro
Dehong
Liu
Gordon
Wichern
William
Yerazunis
Bret
Harsham
Suhas
Lohit
Philip
Orlik
Ye
Wang
Yebin
Wang
Siddarth
Jain
Takashi
Morimoto
Kuan-Chuan
Peng
-
Awards
-
AWARD MERL Researchers win Best Paper Award at ICCV 2019 Workshop on Statistical Deep Learning in Computer Vision Date: October 27, 2019
Awarded to: Abhinav Kumar, Tim K. Marks, Wenxuan Mou, Chen Feng, Xiaoming Liu
MERL Contact: Tim Marks
Research Areas: Artificial Intelligence, Computer Vision, Machine LearningBrief- MERL researcher Tim Marks, former MERL interns Abhinav Kumar and Wenxuan Mou, and MERL consultants Professor Chen Feng (NYU) and Professor Xiaoming Liu (MSU) received the Best Oral Paper Award at the IEEE/CVF International Conference on Computer Vision (ICCV) 2019 Workshop on Statistical Deep Learning in Computer Vision (SDL-CV) held in Seoul, Korea. Their paper, entitled "UGLLI Face Alignment: Estimating Uncertainty with Gaussian Log-Likelihood Loss," describes a method which, given an image of a face, estimates not only the locations of facial landmarks but also the uncertainty of each landmark location estimate.
-
AWARD R&D100 award for Deep Learning-based Water Detector Date: November 16, 2018
Awarded to: Ziming Zhang, Alan Sullivan, Hideaki Maehara, Kenji Taira, Kazuo Sugimoto
MERL Contact: Alan Sullivan
Research Areas: Artificial Intelligence, Computer Vision, Machine LearningBrief- Researchers and developers from MERL, Mitsubishi Electric and Mitsubishi Electric Engineering (MEE) have been recognized with an R&D100 award for the development of a deep learning-based water detector. Automatic detection of water levels in rivers and streams is critical for early warning of flash flooding. Existing systems require a height gauge be placed in the river or stream, something that is costly and sometimes impossible. The new deep learning-based water detector uses only images from a video camera along with 3D measurements of the river valley to determine water levels and warn of potential flooding. The system is robust to lighting and weather conditions working well during the night as well as during fog or rain. Deep learning is a relatively new technique that uses neural networks and AI that are trained from real data to perform human-level recognition tasks. This work is powered by Mitsubishi Electric's Maisart AI technology.
-
AWARD CVPR 2011 Longuet-Higgins Prize Date: June 25, 2011
Awarded to: Paul A. Viola and Michael J. Jones
Awarded for: "Rapid Object Detection using a Boosted Cascade of Simple Features"
Awarded by: Conference on Computer Vision and Pattern Recognition (CVPR)
MERL Contact: Michael Jones
Research Area: Machine LearningBrief- Paper from 10 years ago with the largest impact on the field: "Rapid Object Detection using a Boosted Cascade of Simple Features", originally published at Conference on Computer Vision and Pattern Recognition (CVPR 2001)
See All Awards for MERL -
-
News & Events
-
NEWS MERL Scientists Presenting 11 Papers at IEEE Global Communications Conference (GLOBECOM) 2019 Date: December 9, 2019 - December 13, 2019
Where: Waikoloa, Hawaii, USA
MERL Contacts: Jianlin Guo; Kyeong Jin (K.J.) Kim; Toshiaki Koike-Akino; Rui Ma; Philip Orlik; Pu (Perry) Wang
Research Areas: Communications, Computer Vision, Machine Learning, Signal Processing, Information SecurityBrief- MERL Signal Processing scientists and collaborators will be presenting 11 papers at the IEEE Global Communications Conference (GLOBECOM) 2019, which is being held in Waikoloa, Hawaii from December 9-13, 2019. Topics to be presented include recent advances in power amplifier, MIMO algorithms, WiFi sensing, video casting, visible light communications, user authentication, vehicular communications, secrecy, and relay systems, including sophisticated machine learning applications. A number of these papers are a result of successful collaboration between MERL and world-leading Universities including: Osaka University, University of New South Wales, Oxford University, Princeton University, South China University of Technology, Massachusetts Institute of Technology and Aalborg University.
GLOBECOM is one of the IEEE Communications Society’s two flagship conferences dedicated to driving innovation in nearly every aspect of communications. Each year, more than 3000 scientific researchers and their management submit proposals for program sessions to be held at the annual conference. Themed “Revolutionizing Communications,” GLOBECOM2019 will feature a comprehensive high-quality technical program including 13 symposia and a variety of tutorials and workshops to share visions and ideas, obtain updates on latest technologies and expand professional and social networking.
- MERL Signal Processing scientists and collaborators will be presenting 11 papers at the IEEE Global Communications Conference (GLOBECOM) 2019, which is being held in Waikoloa, Hawaii from December 9-13, 2019. Topics to be presented include recent advances in power amplifier, MIMO algorithms, WiFi sensing, video casting, visible light communications, user authentication, vehicular communications, secrecy, and relay systems, including sophisticated machine learning applications. A number of these papers are a result of successful collaboration between MERL and world-leading Universities including: Osaka University, University of New South Wales, Oxford University, Princeton University, South China University of Technology, Massachusetts Institute of Technology and Aalborg University.
-
NEWS MERL presenting 16 papers at ICASSP 2019 Date: May 12, 2019 - May 17, 2019
Where: Brighton, UK
MERL Contacts: Petros Boufounos; Anoop Cherian; Chiori Hori; Takaaki Hori; Toshiaki Koike-Akino; Jonathan Le Roux; Dehong Liu; Hassan Mansour; Tim Marks; Niko Moritz; Philip Orlik; Anthony Vetro; Pu (Perry) Wang; Gordon Wichern
Research Areas: Computational Sensing, Computer Vision, Machine Learning, Signal Processing, Speech & AudioBrief- MERL researchers will be presenting 16 papers at the IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP), which is being held in Brighton, UK from May 12-17, 2019. Topics to be presented include recent advances in speech recognition, audio processing, scene understanding, computational sensing, and parameter estimation. MERL is also a sponsor of the conference and will be participating in the student career luncheon; please join us at the lunch to learn about our internship program and career opportunities.
ICASSP is the flagship conference of the IEEE Signal Processing Society, and the world's largest and most comprehensive technical conference focused on the research advances and latest technological development in signal and information processing. The event attracts more than 2000 participants each year.
- MERL researchers will be presenting 16 papers at the IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP), which is being held in Brighton, UK from May 12-17, 2019. Topics to be presented include recent advances in speech recognition, audio processing, scene understanding, computational sensing, and parameter estimation. MERL is also a sponsor of the conference and will be participating in the student career luncheon; please join us at the lunch to learn about our internship program and career opportunities.
See All News & Events for Computer Vision -
-
Research Highlights
-
Internships
-
SP1419: Simulation of Multimodal Sensors
MERL is seeking a motivated intern to assist in generating simulated multimodal data for machine learning applications. The project involves integrating several existing software components to generate optical and radar data in a variety of sensing scenarios, and executing the simulations under a variety of conditions. The ideal candidate should have experience with C++, Python, and scripting methods. Some knowledge or experience with Blender, computer graphics, and computer vision would be preferred, but is not required. Project duration is flexible in the range of 1-2 months. Intern has the choice of part-time or full-time occupation and may start immediately.
-
CV1372: Computer Vision for Biased or Scarce Data
MERL is looking for a self-motivated intern to work on data scarcity and bias issues for computer vision. The topics in the scope include (but not limited to): domain adaptation, generative modeling, transfer/low-shot/unsupervised/webly-supervised learning, etc. The ideal candidate would be a PhD student with a strong background in computer vision and machine learning. Proficiency in Python programming and familiarity in at least one deep learning framework are necessary. The ideal candidate is expected to collaborate with MERL researchers to develop algorithms and prepare manuscripts for scientific publications. The duration of the internship is expected to be at least 3 months with a flexible start date.
-
CV1422: Generative Adversarial Networks (GANs)
Generative adversarial networks (GANs) and related methods have generated much excitement for their ability to synthesize images and data that appear remarkably realistic. MERL is seeking a highly motivated intern to conduct original research in the area of generative adversarial networks. The successful candidate will collaborate with MERL researchers to design and implement new models, conduct experiments, and prepare results for publication. The candidate should be a PhD student in computer vision with experience in GANs and related deep learning methods, as well as good general knowledge in machine learning and a strong publication record. Strong programming skills in Python, flexibility working across various deep learning platforms (e.g., PyTorch and TensorFlow), and previous experience coding GANs are expected.
See All Internships for Computer Vision -
-
Openings
See All Openings at MERL -
Recent Publications
- , "DynamicsExplorer: Visual Analytics for Robot Control Tasks involving Dynamics and LSTM-based Control Policies", IEEE Pacific Visualization Symposium (PacificVis), January 2020.BibTeX Download PDFAbout TR2020-011
- @inproceedings{He2020jan,
- author = {He, Wenbin and Lee, Teng-Yok and van Baar, Jeroen and Wittenburg, Kent B. and Shen, Han-Wei},
- title = {DynamicsExplorer: Visual Analytics for Robot Control Tasks involving Dynamics and LSTM-based Control Policies},
- booktitle = {IEEE Pacific Visualization Symposium (PacificVis)},
- year = 2020,
- month = jan,
- url = {https://www.merl.com/publications/TR2020-011}
- }
- , "Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering", IEEE Transactions on Image Processing, January 2020.BibTeX Download PDFAbout TR2020-004
- @article{Chen2020jan,
- author = {Chen, Siheng and Duan, Chaojing and Yang, Yaoqing and Feng, Chen and Li, Duanshun and Tian, Dong},
- title = {Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering},
- journal = {IEEE Transactions on Image Processing},
- year = 2020,
- month = jan,
- url = {https://www.merl.com/publications/TR2020-004}
- }
- , "Unsupervised Deep Feature Transfer for Low Resolution Image Classification", IEEE International Conference on Computer Vision Workshops (ICCV), October 2019.BibTeX Download PDFAbout TR2019-127
- @inproceedings{Zhang2019oct,
- author = {Zhang, Ziming and Wu, Yuanwei and Wang, Guanghui},
- title = {Unsupervised Deep Feature Transfer for Low Resolution Image Classification},
- booktitle = {IEEE International Conference on Computer Vision Workshops (ICCV)},
- year = 2019,
- month = oct,
- url = {https://www.merl.com/publications/TR2019-127}
- }
- , "Unsupervised Joint 3D Object Model Learning and 6D Pose Estimation for Depth-Based Instance Segmentation", IEEE ICCV Workshop on Recovering 6D Object Pose, October 2019.BibTeX Download PDFAbout TR2019-118
- @inproceedings{Wu2019oct,
- author = {Wu, Yuanwei and Marks, Tim and Cherian, Anoop and Chen, Siheng and Feng, Chen and Wang, Guanghui and Sullivan, Alan},
- title = {Unsupervised Joint 3D Object Model Learning and 6D Pose Estimation for Depth-Based Instance Segmentation},
- booktitle = {IEEE ICCV Workshop on Recovering 6D Object Pose},
- year = 2019,
- month = oct,
- url = {https://www.merl.com/publications/TR2019-118}
- }
- , "UGLLI Face Alignment: Estimating Uncertainty with Gaussian Log-Likelihood Loss", IEEE International Conference on Computer Vision (ICCV) Workshop on Statistical Deep Learning for Computer Vision (SDL-CV), October 2019.BibTeX Download PDFAbout TR2019-117
- @inproceedings{Marks2019oct,
- author = {Marks, Tim and Kumar, Abhinav and Mou, Wenxuan and Feng, Chen and Liu, Xiaoming},
- title = {UGLLI Face Alignment: Estimating Uncertainty with Gaussian Log-Likelihood Loss},
- booktitle = {IEEE International Conference on Computer Vision (ICCV) Workshop on Statistical Deep Learning for Computer Vision (SDL-CV)},
- year = 2019,
- month = oct,
- url = {https://www.merl.com/publications/TR2019-117}
- }
- , "Learning from Trajectories via Subgoal Discovery", Advances in Neural Information Processing Systems (NeurIPS), pp. 8409-8419, October 2019.BibTeX Download PDFAbout TR2019-128
- @article{Paul2019oct,
- author = {Paul, Sujoy and van Baar, Jeroen and Roy-Chowdhury, Amit K.},
- title = {Learning from Trajectories via Subgoal Discovery},
- journal = {Advances in Neural Information Processing Systems (NeurIPS)},
- year = 2019,
- pages = {8409--8419},
- month = oct,
- url = {https://www.merl.com/publications/TR2019-128}
- }
- , "GODS: Generalized One-class Discriminative Subspaces for Anomaly Detection", IEEE International Conference on Computer Vision (ICCV), October 2019.BibTeX Download PDFAbout TR2019-121
- @inproceedings{Wang2019oct2,
- author = {Wang, Jue and Cherian, Anoop},
- title = {GODS: Generalized One-class Discriminative Subspaces for Anomaly Detection},
- booktitle = {IEEE International Conference on Computer Vision (ICCV)},
- year = 2019,
- month = oct,
- url = {https://www.merl.com/publications/TR2019-121}
- }
- , "Detection, Tracking and 3D Modeling of Objects with Sparse RGB-D SLAM and Interactive Perception", IEEE-RAS International Conference on Humanoid Robots, October 2019.BibTeX Download PDFAbout TR2019-119
- @inproceedings{Almeida2019oct,
- author = {Almeida, Diogo and Ataer-Cansizoglu, Esra and Corcodel, Radu},
- title = {Detection, Tracking and 3D Modeling of Objects with Sparse RGB-D SLAM and Interactive Perception},
- booktitle = {IEEE-RAS International Conference on Humanoid Robots},
- year = 2019,
- month = oct,
- url = {https://www.merl.com/publications/TR2019-119}
- }
- , "DynamicsExplorer: Visual Analytics for Robot Control Tasks involving Dynamics and LSTM-based Control Policies", IEEE Pacific Visualization Symposium (PacificVis), January 2020.
-
Videos
-
Calibration of Non-Overlapping Cameras Using an External SLAM System
-
Gaussian Conditional Random Field Network for Semantic Segmentation
-
Fast Plane Extraction in Organized Point Clouds Using Agglomerative Hierarchical Clustering
-
Fast Graspability Evaluation on Single Depth Maps for Bin Picking with General Grippers
-
Point-Plane SLAM for Hand-Held 3D Sensors
-
FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds
-
CASENet: Deep Category-Aware Semantic Edge Detection
-
Pinpoint SLAM: A Hybrid of 2D and 3D Simultaneous Localization and Mapping for RGB-D Sensors
-
MERL Research on Autonomous Vehicles
-
Tracking an RGB-D Camera Using Points and Planes
-
Voting-Based Pose Estimation for Robotic Assembly Using a 3D Sensor
-
3D Reconstruction
-
Learning to rank 3D features
-
Fast Object Localization and Pose Estimation in Heavy Clutter for Robotic Bin Picking
-
Deep Hierarchical Parsing for Semantic Segmentation
-
Global Local Face Upsampling Network
-
3D Object Discovery and Modeling Using Single RGB-D Images Containing Multiple Object Instances
-
Joint 3D Reconstruction of a Static Scene and Moving Objects
-
Direct Multichannel Tracking
-
Saffron - Digital Type System
-
Obstacle Detection
-
Semantic Scene Labeling
-
Action Detection Using A Deep Recurrent Neural Network
-
Robot Bin Picking
-
Object Detection and Tracking in RGB-D SLAM via Hierarchical Feature Grouping
-
Dose optimization for particle beam therapy
-
Sapphire - High Accuracy NC Milling Simulation
-
FasTFit: A fast T-spline fitting algorithm
-
-
Free Downloads
